"Enabling deep research modes in AI tools like Kimi and ChatGPT" matching MCP servers:

基于REST API的Kimi Code CLI调试隧道，提供推送式全自动化session编排，支持多轮对话、实时流式响应和智能思考过滤。

Docker MCP ChatGPT Sandbox is a self-hosted remote MCP server for ChatGPT that runs shell commands and edits code inside a hardened Ubuntu container, with OAuth via Keycloak and optional Cloudflare Tunnel.

Enables ChatGPT web to use local tools like file reading, command execution, and patch application through an MCP server over OpenAI Secure MCP Tunnel.

Enables Codex to manage a local Claude Code companion through MCP, implementing a dual-agent workflow where Codex handles reasoning and review while Claude Code performs engineering tasks.

Self-hosted MCP server that lets ChatGPT work with your local codebase through explicit tools.

Enables ChatGPT to read and edit local project files, inspect Git changes, and run approved development scripts through a secure MCP tunnel, with optional Codex Desktop integration.

Enables ChatGPT to securely inspect and administer a Linux VPS over Streamable HTTP, with OAuth protection, workspace file tools, and optional root command execution.

Enables ChatGPT to safely interact with Windows workspaces through a loopback-only MCP server, with OAuth, bounded PowerShell tools, persistent jobs, and optional Cloudflare Tunnel exposure.

Enables conversations to delegate natural-language engineering tasks to a local CLI coding agent in operator-approved workspaces via MCP, with sandbox modes, write gating, bounded execution, and redacted results.

Enables users to run remote commands, inspect projects, transfer files, and execute scripts on authorized Linux servers through natural-language tool calls. It supports listing servers and groups, executing commands individually or across groups, and uploading or downloading files over secure connections.

Enables ChatGPT web to interact with local Windows/WSL shell and code workspaces via an MCP server, providing file access, shell execution, and snapshot-based workspace management with per-command authorization.

MCP server wrapping DeepSeek's agent harness tools into minimal/standard modes, enabling persistent shell, file editing, search, job management, and more via natural language.

Enables dynamic creation and execution of custom tools/functions in multiple programming languages at runtime, exposing them to MCP clients like Claude.

A SQL Server CLI and MCP server for Claude Code that supports standard SQL Server authentication for database interaction and management. It enables users to perform schema exploration, execute queries, and manage data records with built-in SQL injection prevention.

MCP server that gives AI coding agents (Claude Code, Cursor, Cline, etc.) access to multiple AI models through Antigravity CLI and OpenAI Codex CLI, enabling mid-conversation model consultation and code review.

A passive MCP server that exposes a toolbox of executable tools (shell, network, HTTP, AI search, SSH, S3 file operations) to autonomous agents via Streamable HTTP, with strong security features including Docker sandboxing and WAF.

Enables ChatGPT Chat Mode to run commands on remote hosts and manage their files through secure connections, with profiles, host-key checks, and bounded responses.

Self-hosted server that lets ChatGPT, Grok, and stdio MCP clients read and write files, run PowerShell/CMD and interactive processes, and drive the Windows desktop through screenshots, window info, clicks, drags, and keyboard input. It connects via OpenAI Secure MCP Tunnels, an OAuth authorization-code + S256 PKCE HTTPS endpoint, or local stdio, exposing 38 tools under the user's own Windows account.

Enables coding agents to perform file, search, patch, git, process, test, package, network, and system operations through 60 typed MCP tools with structured inputs/outputs, structured errors, and a full event journal, replacing terminal use with a typed machine API.

Enables agent clients to safely connect to tools and execution resources through MCP with authorization, approvals, audit, chat-context isolation, SSH/Docker access, and long-running command session tracking.

Enables AI agents to turn local projects into persistent workspaces, providing file editing, command execution, Git integration, and cross-session history management.

A Rust + Tauri 2 desktop application that turns local project folders into persistent MCP workspaces, enabling AI agents to read files, modify code, run commands and tests, check Git status, and maintain cross-conversation development context through historical checkpoints, with built-in WSS/FRP/Cloudflare tunnels and OAuth for connecting to ChatGPT.

Enables ChatGPT to remotely orchestrate local Codex and Claude Code agents for file editing and command execution via a secure Cloudflare tunnel, bridging cloud AI planning with local execution.

Enables ChatGPT Web to discover and invoke native local Codex tools via OpenAI's Secure MCP Tunnel, with the local host executing commands and returning results.

Enables ChatGPT's web interface to operate a real Mac by executing shell commands and reading or writing files over a reverse SSH tunnel, without installing a client or consuming API quota.

Enables ChatGPT to operate a local workstation through a secure outbound tunnel, exposing 44 MCP tools for files, git, projects, processes, browsers, native apps, Office documents, and optional Codex delegation across macOS, Linux, and Windows.

An unofficial self-hosted MCP server that enables ChatGPT to run commands on your computer through a secure tunnel, manage processes, and work within a specified project directory.

Enables AI agents to run passive, boundary, and gated active reconnaissance and web-security CLI tools (nmap, sqlmap, commix, httpx, ffuf, nikto, subfinder, and more) against authorized targets through a persistent, API-key-protected HTTP service. Scope gates, authorization windows, evidence capture, and a full audit trail are enforced in code so every tool call stays within the engagement's declared rules.

Enables MCP clients to invoke common Kali Linux pentesting tools directly as tool calls, with each binary executed safely without a shell.

Enables running multiple AI CLI tools (Claude, Codex, Gemini, Forge, OpenCode) as background processes with automatic permission handling, allowing LLMs to execute async multitasking and combine different AI models.